Eight Sleep Logout

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the destructiveHint annotation, the description adds crucial specifics: the exact artifact destroyed (token file on disk), the scope (local-only), the consent requirement, and the exemption from the environment mutation flag. This fully informs the agent of the behavioral and safety profile.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two tight sentences with the primary action front-loaded. Every clause adds meaningful information, and there is no redundant or filler language.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive local mutation, the description covers what is deleted, the local scope, the consent gate, and the safety flag interaction. It does not describe output details, but an output schema exists, so that responsibility is already handled.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema already describes explicit_user_intent, and the description reinforces its role in gating the action. However, response_format has no description in the schema and is not mentioned in the description either; the enum values are self-explanatory, so the partial 50% coverage is only partially compensated.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a concrete action and resource: 'Delete the local Eight Sleep token file.' This unambiguously identifies the logout behavior and distinguishes it from the many get/set/profile siblings by specifying exactly what is affected.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description clearly indicates when the tool is permitted: it requires explicit user intent/consent and is not gated by EIGHT_SLEEP_ALLOW_MUTATIONS. While it does not explicitly name alternative tools, no sibling tool offers the same token-clearing logout function, so the usage context is sufficiently clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.